Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/celineycn/quantdata-plugin/quantdata-daily-biasnpx skills add celineycn/quantdata-plugin --skill quantdata-daily-biasgit clone --depth 1 https://github.com/celineycn/quantdata-pluginWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00167 | $0.09179 |
| Opus 5 | $0.00084 | $0.04589 |
| Sonnet 5 | $0.00033 | $0.01836 |
| Haiku 4.5 | $0.00017 | $0.00918 |
Grade A, and why
quantdata-daily-bias scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "X-API-Key: $QUANTDATA_API_KEY" \ How it starts
The opening of the file, as written. The whole thing — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quant Data — Brooks Events
An HTTP API that detects the classical Brooks price-action events in the window trading right now and attaches to each one the outcome rate measured for that exact event definition in that exact window — pre-registered, on sixteen years of S&P 500 futures data. Range breakouts additionally carry a calibrated per-event failure estimate.
Two further blocks travel with every read and answer different questions. day_type is a
calibrated probability distribution over how the session in progress could resolve — a
prediction, with published accuracy, available in the US day session only. shape is
arithmetic over the bars that have already printed — a measurement, with no accuracy figure
because nothing is being predicted, available in every window. Keeping those two apart is a
hard rule of this skill; see "Two blocks that are not the same thing" below.
Base URL: https://api.quantdata.uk
Authentication
Send the header X-API-Key, with a key starting qd_. Read it from the environment variable
QUANTDATA_API_KEY. Never write a key into this file, into code you generate, into a
commit, or into a message back to the user.
export QUANTDATA_API_KEY="qd_..."
If the variable is unset, one anonymous first-look response may still succeed per source per
UTC day. It is a complete response, and its legacy-named free_tier object has
access_kind: "anonymous", calls_remaining_today, resets_at, and the next action.
For continued evaluation, ask the user which email address should receive a free key, then
POST https://api.quantdata.uk/v1/access/free-key with JSON:
{"email":"[email protected]","marketing_opt_in":false,"source":"agent"}
An MCP-connected agent can call quantdata_request_free_api_key instead. No login, password,
card or GUI is required. The raw qd_ key is delivered only to the inbox and never returned in
the REST or MCP result. Never invent an email address.
marketing_opt_in defaults to false and is separate from key delivery. Set it to true only
when the email owner explicitly asks for occasional product updates. A true request is only
pending. It is confirmed only if the recipient replies SUBSCRIBE to the key-delivery email;
no marketing updates are sent before confirmation. Do not report the request as a completed
subscription. A free key covers all four Quant Data endpoints, sharing 10 successful calls
per UTC day.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 566 lines · 167 tokens per session scan A b2dcd225c50c
quantdata-daily-bias is a skill published in the GitHub repository celineycn/quantdata-plugin (1 stars, last pushed 15d ago), licensed MIT. It adds 167 tokens to every session and 9,179 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
correlation-analysis
Correlation and cointegration analysis — co-movement discovery, deep return-correlation analysis, sector clustering, realized correlation, Engle-Granger / Johansen cointegration, half-life, Kalman dynamic hedge ratio, cross-market linkage analysis, and pair-trading signal generation.
ashare-pre-st-filter
A 股 ST/ST 风险预测框架 — 基于最新中报/三季报或业绩预告/快报，预测下一财年是否会因营收、利润、净资产、分红不达标而被风险警示，并将新浪监管处罚记录作为独立证据面纳入风险等级。仅适用于 A 股，不预测财务造假。.
credit-analysis
固收与信用分析：信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略。.
geopolitical-risk
Geopolitical risk analysis: quantify crisis signals, identify precursors, and build event-driven strategies for war, sanctions, and supply disruption scenarios.
vibe-trading
Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 90 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract →…
etf-analysis
ETF分析：产品筛选、费率对比、跟踪误差、流动性评估、策略应用与中国市场ETF量化配置框架。.